What is the CZ CELLxGENE Census?

The CZ CELLxGENE Census is a comprehensive, versioned collection of standardized single-cell genomics data from CZ CELLxGENE Discover, providing programmatic access to millions of cells.

How do I avoid duplicate cells in my analysis?

The skill provides patterns that recommend always filtering for 'is_primary_data == True' in your queries to ensure you are analyzing unique cells.

How do I ensure my research is reproducible?

The skill emphasizes specifying the 'census_version' when opening the data to ensure that analyses can be replicated against exact data snapshots.

Can I use this for machine learning?

Yes, this skill includes specific patterns for integrating Census data with PyTorch using experimental data loaders designed for large-scale model training.

Does this skill handle memory-intensive queries?

Yes, it provides workflows for out-of-core processing using axis_query and iterative processing to handle datasets that exceed available system RAM.

CZ CELLxGENE Census Data Analysis

Name: CZ CELLxGENE Census Data Analysis
Author: BbgnsurfTech

byBbgnsurfTech

•

データサイエンスとML

Enables programmatic access and analysis of the CZ CELLxGENE Census, a collection of over 61 million standardized single-cell genomics records.

概要

This skill provides specialized guidance and implementation patterns for interacting with the CZ CELLxGENE Census, allowing researchers and developers to query massive single-cell genomics datasets across thousands of studies. It facilitates efficient filtering by cell type, tissue, and disease, enables the retrieval of raw gene expression matrices, and provides seamless integration with popular analysis frameworks like scanpy and PyTorch for population-scale bioinformatics and machine learning workflows.

主な機能

3 GitHub stars
Filter data by standardized cell type, tissue, and disease metadata
Seamless interoperability with scanpy analysis pipelines
Query 61M+ cells from human and mouse datasets
Stream large-scale expression data for out-of-core processing
Direct integration with PyTorch for ML model training

ユースケース

Performing cross-dataset single-cell expression analysis
Training machine learning models on population-scale genomics data
Exploring cell-type specific gene expression across multiple tissues

概要

主な機能

3 GitHub stars
Filter data by standardized cell type, tissue, and disease metadata
Seamless interoperability with scanpy analysis pipelines
Query 61M+ cells from human and mouse datasets
Stream large-scale expression data for out-of-core processing
Direct integration with PyTorch for ML model training

ユースケース

Performing cross-dataset single-cell expression analysis
Training machine learning models on population-scale genomics data
Exploring cell-type specific gene expression across multiple tissues